Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Seo, Seokjun"'
Autor:
Han, Seungju, Kim, Beomsu, Yoo, Jin Yong, Seo, Seokjun, Kim, Sangbum, Erdenee, Enkhbayar, Chang, Buru
In this paper, we consider mimicking fictional characters as a promising direction for building engaging conversation models. To this end, we present a new practical task where only a few utterances of each fictional character are available to genera
Externí odkaz:
http://arxiv.org/abs/2204.10825
Exemplar-based generative models for open-domain conversation produce responses based on the exemplars provided by the retriever, taking advantage of generative models and retrieval models. However, they often ignore the retrieved exemplars while gen
Externí odkaz:
http://arxiv.org/abs/2112.06723
Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due to high latency. On the other hand, retrieval models could return res
Externí odkaz:
http://arxiv.org/abs/2108.12582
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the uniform target label distribution. Such protocol has questionable prac
Externí odkaz:
http://arxiv.org/abs/2012.00321
When there is a mismatch between the target identity and the driver identity, face reenactment suffers severe degradation in the quality of the result, especially in a few-shot setting. The identity preservation problem, where the model loses the det
Externí odkaz:
http://arxiv.org/abs/1911.08139
Autor:
Seo, Seokjun, Choi, Seungwoo, Kersner, Martin, Shin, Beomjun, Yoon, Hyungsuk, Byun, Hyeongmin, Ha, Sungjoo
We tackle the problem of automatic portrait matting on mobile devices. The proposed model is aimed at attaining real-time inference on mobile devices with minimal degradation of model performance. Our model MMNet, based on multi-branch dilated convol
Externí odkaz:
http://arxiv.org/abs/1904.03816
Autor:
Choi, Seungwoo, Seo, Seokjun, Shin, Beomjun, Byun, Hyeongmin, Kersner, Martin, Kim, Beomsu, Kim, Dongyoung, Ha, Sungjoo
Keyword spotting (KWS) plays a critical role in enabling speech-based user interactions on smart devices. Recent developments in the field of deep learning have led to wide adoption of convolutional neural networks (CNNs) in KWS systems due to their
Externí odkaz:
http://arxiv.org/abs/1904.03814
Autor:
Lee, YongKwan, Kim, HyunChul, Kwon, Namhun, Sim, JaeJin, Lee, MiHye, Oh, SoongJu, Seo, SeokJun, Shin, JaeHong, Park, Kyoungtae
Publikováno v:
In International Journal of Refractory Metals and Hard Materials April 2023 112
Network biology has been successfully used to help reveal complex mechanisms of disease, especially cancer. On the other hand, network biology requires in-depth knowledge to construct disease-specific networks, but our current knowledge is very limit
Externí odkaz:
http://arxiv.org/abs/1711.05859
Autor:
Chae, Heejoon, Lee, Sangseon, Seo, Seokjun, Jung, Daekyoung, Chang, Hyeonsook, Nephew, Kenneth P., Kim, Sun
Publikováno v:
In Methods 1 December 2016 111:64-71